© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 53245
    Prev
    Next
    INDEX
    Explanations

    web page or document content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ती
    0.50
    ੀ
    0.47
    たま
    0.45
    racial
    0.43
    deeds
    0.43
    endem
    0.43
    snp
    0.42
    bygg
    0.42
    ร้อม
    0.42
     सऊदी
    0.42
    POSITIVE LOGITS
     I
    0.49
     a
    0.48
     horizontal
    0.48
     overwrite
    0.47
     VMware
    0.46
     übertragen
    0.46
     Ic
    0.45
     beeinfl
    0.45
     automotive
    0.44
     nouveau
    0.44
    Activations Density 0.002%

    No Known Activations